Structured Memory based Deep Model to Detect as well as Characterize Novel Inputs

نویسندگان

  • Pratik Prabhanjan Brahma
  • Qiuyuan Huang
  • Dapeng Wu
چکیده

While deep learning has pushed the boundaries in various machine learning tasks, the current models are still far away from replicating many functions that a normal human brain can do. Explicit memorization based deep architecture have been recently proposed with the objective to understand and predict better. In this work, we design a system that involves a primary learner and an adjacent representational memory bank which is organized using a comparative learner. This spatially forked deep architecture with a structured memory can simultaneously predict and reason about the nature of an input, which may even belong to a category never seen in the training data, by relating it with the memorized past representations at the higher layers. Characterizing images of unseen object classes in both synthetic and real world datasets is used as an example to showcase the operational success of the proposed framework.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Integration of remote sensing and meteorological data to predict flooding time using deep learning algorithm

Accurate flood forecasting is a vital need to reduce its risks. Due to the complicated structure of flood and river flow, it is somehow difficult to solve this problem. Artificial neural networks, such as frequent neural networks, offer good performance in time series data. In recent years, the use of Long Short Term Memory networks hase attracted much attention due to the faults of frequent ne...

متن کامل

Named Entity Recognition in Persian Text using Deep Learning

Named entities recognition is a fundamental task in the field of natural language processing. It is also known as a subset of information extraction. The process of recognizing named entities aims at finding proper nouns in the text and classifying them into predetermined classes such as names of people, organizations, and places. In this paper, we propose a named entity recognizer which benefi...

متن کامل

FPGA Implementation of a Hammerstein Based Digital Predistorter for Linearizing RF Power Amplifiers with Memory Effects

Power amplifiers (PAs) are inherently nonlinear elements and digital predistortion is a highly cost-effective approach to linearize them. Although most existing architectures assume that the PA has a memoryless nonlinearity, memory effects of the PAs in many applications ,such as wideband code-division multiple access (WCDMA) or orthogonal frequency-division multiplexing (OFDM), can no longer b...

متن کامل

Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets

Graphs provide a powerful means for representing complex interactions between entities. Recently, new deep learning approaches have emerged for representing and modeling graphstructured data while the conventional deep learning methods, such as convolutional neural networks and recurrent neural networks, have mainly focused on the grid-structured inputs of image and audio. Leveraged by represen...

متن کامل

A Study on Expert Primary School Teachers’ Deep Insight and a Model to Develop that in Student Teachers

The present research has endeavored to study deep insight experiences of expert teachers of primary schools as an effort to provide a model to be expanded for student teachers to use. Taking a qualitative approach, the research used narrative inquiry. The statistical population consisted of primary school teachers. Snowball sampling was used, and data collection and analysis were carried out by...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1801.09859  شماره 

صفحات  -

تاریخ انتشار 2018